INDEX

Explanations

repetitive patterns or mentions of specific functions and variables in code, particularly related to logging and traceability

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.87

“

-0.81

<eos>

-0.65

↵↵

-0.60

at

-0.60

-0.58

-0.52

（

-0.51

“

-0.51

-0.50

POSITIVE LOGITS

 متعلقه

1.70

 iſt

1.09

 المعيارى

1.06

Efq

1.05

ReusableCell

1.04

 وتسجيلات

1.04

 createState

1.03

 שוליים

1.02

 مشين

1.01

 houſe

0.99

Activations Density 0.471%

repetitive patterns or mentions of specific functions and variables in code, particularly related to logging and traceability

No Comments

No Known Activations